knn: k-Nearest Neighbour k-nearest neighbour...

In Fuzzy-Logix/AdapteR: Converts R syntax to SQL to provide fast analytics using in-database C++ library DB Lytix.

Description

k-Nearest Neighbour k-nearest neighbour classification/Regression for test set from training set. For each row of the test set, the k nearest (according to distance metric speicified) training set vectors are found, and the classification is decided by majority vote, with ties broken at random. If there are ties for the kth nearest vector, all candidates are included in the vote. If classify flag is false, average of k neighbours is returned.

Usage

knn(train, test = train, cl = "NULL", k = 1, l = 0, prob = FALSE,
  use.all = FALSE, ...)

Arguments

train	input deep FLTable
test	input deep FLTable
cl	ColumnName of true classifications of training set
k	number of neighbours considered.
prob	If this is true, the proportion of the votes for the winning class are returned as attribute prob.
classify	logical if classification/regression is solved
metric	distance metric to be used. euclidean, manhattan supported.

Value

FLVector of classifications of test set.

Examples

FLdeepTbl <- FLTable(getTestTableName("ARknnDevSmall"),"obsid","varid","num_val")
FLknnOutput <- knn(FLdeepTbl,k=3,prob=TRUE)
FLknnOutput
attributes(FLknnOutput)$prob

Fuzzy-Logix/AdapteR documentation built on May 6, 2019, 5:07 p.m.